Compressed Sensing MRI Using Sparsity Averaging and FISTA

Magnetic resonance imaging (MRI) is widely adopted for clinical diagnosis due to its non-invasively detection. However, acquisition of full k-space data limits its imaging speed. Compressed sensing (CS) provides a new technique to significantly reduce the measurements with high-quality MR image reconstruction. The sparsity of the MR images is one of the crucial bases of CS-MRI. In this paper, we present to use sparsity averaging prior for CS-MRI reconstruction in the basis of that MR images have average sparsity over multiple wavelet frames. The problem is solved using a Fast Iterative Shrinkage Thresholding Algorithm (FISTA), each iteration of which includes a shrinkage step. The performance of the proposed method is evaluated for several types of MR images. The experiment results illustrate that our approach exhibits a better performance than those methods that using redundant frame or a single orthonormal basis to promote sparsity.     

双树小波变换与小波树稀疏联合的低场CS-MRI算法

压缩感知理论常用在磁共振快速成像上,仅采样少量的K空间数据即可重建出高质量的磁共振图像.压缩感知磁共振成像技术的原理是将磁共振图像重建问题建模成一个包含数据保真项、稀疏先验项和全变分项的线性组合最小化问题,显著减少磁共振扫描时间.稀疏表示是压缩感知理论的一个关键假设,重建结果很大程度上依赖于稀疏变换.本文将双树复小波变换和小波树稀疏联合作为压缩感知磁共振成像中的稀疏变换,提出了基于双树小波变换和小波树稀疏的压缩感知低场磁共振图像重建算法.实验表明,本文所提算法可以在某些磁共振图像客观评价指标中表现出一定的优势.     

Fast multi-contrast MRI reconstruction

Multi-contrast magnetic resonance imaging (MRI) is a useful technique to aid clinical diagnosis. This paper proposes an efficient algorithm to jointly reconstruct multiple T1/T2-weighted images of the same anatomical cross section from partially sampled k-space data. The joint reconstruction problem is formulated as minimizing a linear combination of three terms, corresponding to a least squares data fitting, joint total variation (TV) and group wavelet-sparsity regularization. It is rooted in two observations: 1) the variance of image gradients should be similar for the same spatial position across multiple contrasts; 2) the wavelet coefficients of all images from the same anatomical cross section should have similar sparse modes. To efficiently solve this problem, we decompose it into joint TV regularization and group sparsity subproblems, respectively. Finally, the reconstructed image is obtained from the weighted average of solutions from the two subproblems, in an iterative framework. Experiments demonstrate the efficiency and effectiveness of the proposed method compared to existing multi-contrast MRI methods.     

选择性双向顺序压缩感知重建动态磁共振成像

压缩感知是一种新兴技术,该技术能够用远低于奈奎斯特采样频率采集的信号恢复出原始信号. 压缩感知成像方法大大提高了心脏磁共振成像的采集速度,已有的方法主要利用动态图像时间相关及心脏的周期性运动特征,如采用在时间维做傅立叶变换或求解每帧数据跟参考帧数据的差异获取稀疏数据,满足压缩感知重建的要求. 该文提出了选择性双向顺序压缩感知重建算法,利用相邻帧的差异更小的特点,获取更加稀疏的差异数据,同时利用动态图像的周期性,以目标函数积分为判据,在时间顺序和时间逆序两个方向选择效果更好的方向进行数据重建,降低图像伪影和噪声. 该选择算法,可以在不增加重建时间的情况下,选择双向顺序重建中最佳的结果. 该文对心脏磁共振图像数据进行了数据处理实验,并且跟传统压缩感知算法、参考帧差异方法及匙孔成像方法进行了比较. 结果表明：该方法无论从视觉效果还是从统计结果上,都有很大的改善.     

CS-MRI 中评价随机欠采样矩阵的新方法

在压缩感知-磁共振成像(CS-MRI)中,随机欠采样矩阵与重建图像质量密切相关．而选取随机欠采样矩阵一般是通过计算点扩散函数(PSF),以可能产生的伪影的最大值为评价参数,评估欠采样对图像重建的影响,然而最大值只反应了伪影的最坏情况．该文引入了两种新的统计学评价参数平均值(MV)和标准差(SD),其中平均值评估了伪影的平均大小,标准差可以反映伪影的波动情况．该文分别使用这3种参数对小鼠和人体脑部MRI数据以不同的采样比率进行CS图像重建,实验结果表明,当采样比率不低于4倍稀疏度时,使用平均值获得了质量更优的重建图像．因此,通过稀疏度先验知识指导合理选取采样比率,并以平均值为评价参数选取随机欠采样矩阵,能够获得更优的CS-MRI重建图像．
     

Triple-D network for efficient undersampled magnetic resonance images reconstruction

Compressed sensing (CS) theory can help accelerate magnetic resonance imaging (MRI) by sampling partial k-space measurements. However, conventional optimization-based CS-MRI methods are often time-consuming and are based on fixed transform or shallow image dictionaries, which limits modeling capabilities. Recently, deep learning models have been used to solve the CS-MRI problem. However, recent researches have focused on modeling in image domain, and the potential of k-space modeling capability has not been utilized seriously. In this paper, we propose a deep model called Dual Domain Dense network (Triple-D network), which consisted of some k-space and image domain sub-network. These sub-networks are connected with dense connections, which can utilize feature maps at different levels to enhance performance. To further promote model capabilities, we use two strategies: multi-supervision strategies, which can avoid loss of supervision information; channel-wise attention layer (CA layer), which can adaptively adjust the weight of the feature map. Experimental results show that the proposed Triple-D network provides promising performance in CS-MRI, and it can effectively work on different sampling trajectories and noisy settings.     

Motion correction based reconstruction method for compressively sampled cardiac MR imaging

Respiratory motion during Magnetic Resonance (MR) acquisition causes strong blurring artifacts in the reconstructed images. These artifacts become more pronounced when used with the fast imaging reconstruction techniques like compressed sensing (CS). Recently, an MR reconstruction technique has been done with the help of compressed sensing (CS), to provide good quality sparse images from the highly under-sampled k-space data. In order to maximize the benefits of CS, it is obvious to use CS with the motion corrected samples. In this paper, we propose a novel CS based motion corrected image reconstruction technique. First, k-space data have been assigned to different respiratory state with the help of frequency domain phase correlation method. Then, multiple sparsity constraints has been used to provide good quality reconstructed cardiac cine images with the highly under-sampled k-space data. The proposed method exploits the multiple sparsity constraints, in combination with demon based registration technique and a novel reconstruction technique to provide the final motion free images. The proposed method is very simple to implement in clinical settings as compared to existing motion corrected methods. The performance of the proposed method is examined using simulated data and clinical data. Results show that this method performs better than the reconstruction of CS based method of cardiac cine images. Different acceleration rates have been used to show the performance of the proposed method.     

Methods for quantitative image quality evaluation of MRI parallel reconstructions: detection and perceptual difference model

Many reconstruction algorithms are being proposed for parallel magnetic resonance imaging (MRI), which uses multiple coils and subsampled k-space data, and a quantitative method for comparison of algorithms is sorely needed. On such images, we compared three methods for quantitative image quality evaluation: human detection, computer detection model and a computer perceptual difference model (PDM). One-quarter sampling and three different reconstruction methods were investigated: a regularization method developed by Ying et al., a simplified regularization method and an iterative method proposed by Pruessmann et al. Images obtained from a full complement of k-space data were also included as reference images. Detection studies were performed using a simulated dark tumor added on MR images of fresh bovine liver. Human detection depended strongly on reconstruction methods used, with the two regularization methods achieving better performance than the iterative method. Images were also evaluated using detection by a channelized Hotelling observer model and by PDM scores. Both predicted the same trends as observed from human detection. We are encouraged that PDM gives trends similar to that for human detection studies. Its ease of use and applicability to a variety of MRI situations make it attractive for evaluating image quality in a variety of MR studies.     

Visually weighted reconstruction of compressive sensing MRI

Compressive sensing (CS) enables the reconstruction of a magnetic resonance (MR) image from undersampled data in k-space with relatively low-quality distortion when compared to the original image. In addition, CS allows the scan time to be significantly reduced. Along with a reduction in the computational overhead, we investigate an effective way to improve visual quality through the use of a weighted optimization algorithm for reconstruction after variable density random undersampling in the phase encoding direction over k-space. In contrast to conventional magnetic resonance imaging (MRI) reconstruction methods, the visual weight, in particular, the region of interest (ROI), is investigated here for quality improvement. In addition, we employ a wavelet transform to analyze the reconstructed image in the space domain and fully utilize data sparsity over the spatial and frequency domains. The visual weight is constructed by reflecting the perceptual characteristics of the human visual system (HVS), and then applied to ?₁ norm minimization, which gives priority to each coefficient during the reconstruction process. Using objective quality assessment metrics, it was found that an image reconstructed using the visual weight has higher local and global quality than those processed by conventional methods.     

IKWI-net: A cross-domain convolutional neural network for undersampled magnetic resonance image reconstruction

Magnetic resonance imaging (MRI) is widely used to get the information of anatomical structure and physiological function with the advantages of high resolution and non-invasive scanning. But the long acquisition time limits its application. To reduce the time consumption of MRI, compressed sensing (CS) theory has been proposed to reconstruct MRI images from undersampled k-space data. But conventional CS methods mostly use iterative methods that take lots of time. Recently, deep learning methods are proposed to achieve faster reconstruction, but most of them only pay attention to a single domain, such as the image domain or k-space. To take advantage of the feature representation in different domains, we propose a cross-domain method based on deep learning, which first uses convolutional neural networks (CNNs) in the image domain, k-space and wavelet domain simultaneously. The combined order of the three domains is also first studied in this work, which has a significant effect on reconstruction. The proposed IKWI-net achieves the best performance in various combinations, which utilizes CNNs in the image domain, k-space, wavelet domain and image domain sequentially. Compared with several deep learning methods, experiments show it also achieves mean improvements of 0.91 dB in peak signal-to-noise ratio (PSNR) and 0.005 in structural similarity (SSIM).     

螺旋MRI的网格化数据重建算法比较

螺旋MRI的原始数据是在不均匀的 k- 空间螺旋轨迹上采样得到的,需要通过网格化算法等手段将数据变成等间距的网格数据后,才能采用FFT进行重建,最后得到供临床使用的图像. 本文对Jackson网格化算法和Claudia大矩阵算法的重建速度和图像结果进行了比较, 并得出以下结论：1）在获得相近图像质量的情况下,Claudia大矩阵重采样算法比Jackson算法要快且更方便在仪器上实现. 2）在Jackson双倍细网格算法的实现方式中,数据驱动插值比网格驱动插值更有效率. 3）在Claudia大矩阵重采样算法中,对冗余比大于310∶1的数据进行图像重建的时候,网格点的幅值不平均化比平均化后的效果还要好. 这几个结论都将有利于MRI图像重建技术的进一步提高.      

Deep neural network inspired by iterative shrinkage-thresholding algorithm with data consistency (NISTAD) for fast Undersampled MRI reconstruction

With the aim of developing a fast algorithm for high-quality MRI reconstruction from undersampled k-space data, we propose a novel deep neural Network, which is inspired by Iterative Shrinkage Thresholding Algorithm with Data consistency (NISTAD). NISTAD consists of three consecutive blocks: an encoding block, which models the flow graph of ISTA, a classical iteration-based compressed sensing magnetic resonance imaging (CS-MRI) method; a decoding block, which recovers the image from sparse representation; a data consistency block, which adaptively enforces consistency with the acquired raw data according to learned noise level. The ISTA method is thereby mapped to an end-to-end deep neural network, which greatly reduces the reconstruction time and simplifies the tuning of hyper-parameters, compared to conventional model-based CS-MRI methods. On the other hand, compared to general deep learning-based MRI reconstruction methods, the proposed method uses a simpler network architecture with fewer parameters. NISTAD has been validated on retrospectively undersampled diencephalon standard challenge data using different acceleration factors, and compared with DAGAN and Cascade CNN, two state-of-the-art deep neural network-based methods which outperformed many other state-of-the-art model-based and deep learning-based methods. Experimental results demonstrated that NISTAD reconstruction achieved comparable image quality with DAGAN and Cascade CNN reconstruction in terms of both PSNR and SSIM metrics, and subjective assessment, though with a simpler network structure.     

Magnetic resonance imaging segmentation techniques using batch-type learning vector quantization algorithms

In this article, we propose batch-type learning vector quantization (LVQ) segmentation techniques for the magnetic resonance (MR) images. Magnetic resonance imaging (MRI) segmentation is an important technique to differentiate abnormal and normal tissues in MR image data. The proposed LVQ segmentation techniques are compared with the generalized Kohonen's competitive learning (GKCL) methods, which were proposed by Lin et al. [Magn Reson Imaging 21 (2003) 863-870]. Three MRI data sets of real cases are used in this article. The first case is from a 2-year-old girl who was diagnosed with retinoblastoma in her left eye. The second case is from a 55-year-old woman who developed complete left side oculomotor palsy immediately after a motor vehicle accident. The third case is from an 84-year-old man who was diagnosed with Alzheimer disease (AD). Our comparisons are based on sensitivity of algorithm parameters, the quality of MRI segmentation with the contrast-to-noise ratio and the accuracy of the region of interest tissue. Overall, the segmentation results from batch-type LVQ algorithms present good accuracy and quality of the segmentation images, and also flexibility of algorithm parameters in all the comparison consequences. The results support that the proposed batch-type LVQ algorithms are better than the previous GKCL algorithms. Specifically, the proposed fuzzy-soft LVQ algorithm works well in segmenting AD MRI data set to accurately measure the hippocampus volume in AD MR images.     

Reduced aliasing artifacts using shaking projection k-space sampling trajectory

Radial imaging techniques, such as projection-reconstruction （PR）, are used in magnetic resonance imaging （MRI） for dynamic imaging, angiography, and short-T2 imaging. They are less sensitive to flow and motion artifacts, and support fast imaging with short echo times. However, aliasing and streaking artifacts are two main sources which degrade radial imaging quality. For a given fixed number of k-space projections, data distributions along radial and angular directions will influence the level of aliasing and streaking artifacts. Conventional radial k-space sampling trajectory introduces an aliasing artifact at the first principal ring of point spread function （PSF）. In this paper, a shaking projection （SP） k-space sampling trajectory was proposed to reduce aliasing artifacts in MR images. SP sampling trajectory shifts the projection alternately along the k-space center, which separates k-space data in the azimuthal direction. Simulations based on conventional and SP sampling trajectories were compared with the same number projections. A significant reduction of aliasing artifacts was observed using the SP sampling trajectory. These two trajectories were also compared with different sampling frequencies. ASP trajectory has the same aliasing character when using half sampling frequency （or half data） for reconstruction. SNR comparisons with different white noise levels show that these two trajectories have the same SNR character. In conclusion, the SP trajectory can reduce the aliasing artifact without decreasing SNR and also provide a way for undersampling recon- struction. Furthermore, this method can be applied to three-dimensional （3D） hybrid or spherical radial k-space sampling for a more efficient reduction of aliasing artifacts.     

Rapid passive MR catheter visualization for endovascular therapy using nonsymmetric truncated k-space sampling strategies

Passive catheter tracking guidance by MRI is a promising approach for endovascular therapy that may have several clinical advantages over the more frequently employed active MR approaches. However, real-time MR passive tracking is problematic because it is difficult to have an image update rate >1 Hz and preserve adequate spatial and image contrast resolution. One solution for improving real-time temporal performance is the use of nonsymmetric truncated k-space sampling strategies, which acquire only a fraction of the data in both the readout and phase-encoding directions. This article investigated these acquisition strategies in combination with using (a) multicycle projection dephaser (mcPD) gradients for background suppression and (b) the projection-onto-convex sets (POCS) algorithm to reconstruct the images. The use of mcPD gradients allowed the data sampling strategies to exploit the k-space energy structure of the catheter, and POCS allowed reconstruction of high-quality MR images that were suitable for real-time passive catheter tracking and demonstrated improved geometric representations of catheter width and tip position compared to zero filling. The use of nonsymmetric truncated k-space reduced the total acquisition time.     

Sparse MRI reconstruction using multi-contrast image guided graph representation

Accelerating the imaging speed without sacrificing image structures plays an important role in magnetic resonance imaging. Under-sampling the k-space data and reconstructing the image with sparsity constraint is one efficient way to reduce the data acquisition time. However, achieving high acceleration factor is challenging since image structures may be lost or blurred when the acquired information is not sufficient. Therefore, incorporating extra knowledge to improve image reconstruction is expected for highly accelerated imaging. Fortunately, multi-contrast images in the same region of interest are usually acquired in magnetic resonance imaging protocols. In this work, we propose a new approach to reconstruct magnetic resonance images by learning the prior knowledge from these multi-contrast images with graph-based wavelet representations. We further formulate the reconstruction as a bi-level optimization problem to allow misalignment between these images. Experiments on realistic imaging datasets demonstrate that the proposed approach improves the image reconstruction significantly and is practical for real world application since patients are unnecessarily to stay still during successive reference image scans.     

Joint reconstruction of multiecho MR images using correlated sparsity

This works addresses the problem of reconstructing multiple T1- or T2-weighted images of the same anatomical cross section from partially sampled K-space data. Previous studies in reconstructing magnetic resonance (MR) images from partial samples of the K-space used compressed sensing (CS) techniques to exploit the spatial correlation of the images (leading to sparsity in wavelet domain). Such techniques can be employed to reconstruct the individual T1- or T2-weighted images. However, in the current context, the different images are not really independent; they are images of the same cross section and, hence, are highly correlated. We exploit the correlation between the images, along with the spatial correlation within the images to achieve better reconstruction results than exploiting spatial correlation only.For individual MR images, CS-based techniques lead to a sparsity-promoting optimization problem in the wavelet domain. In this article, we show that the same framework can be extended to incorporate correlation between images leading to group/row sparsity-promoting optimization. Algorithms for solving such optimization problems have already been developed in the CS literature. We show that significant improvement in reconstruction accuracy can be achieved by considering the correlation between different T1- and T2-weighted images. If the reconstruction accuracy is considered to be constant, our proposed group sparse formulation can yield the same result with 33% less K-space samples compared with simple sparsity-promoting reconstruction. Moreover, the reconstruction time by our proposed method is about two to four times less than the previous method.     

Phase correction-based singularity function analysis for partial k-space reconstruction

Partial k-space acquisition is a conventional method in magnetic resonance imaging (MRI) for reducing imaging time while maintaining image quality. In this field, image reconstruction from partial k-space is a key issue. This paper proposes an approach fundamentally different from traditional techniques for reconstructing magnetic resonance (MR) images from partial k-space. It uses a so-called singularity function analysis (SFA) model based on phase correction. With such a reconstruction approach, some nonacquired negative spatial frequencies are first recovered by means of phase correction and Hermitian symmetry property, and then the other nonacquired negative and/or positive spatial frequencies are estimated using the mathematical SFA model. The method is particularly suitable for asymmetrical partial k-space acquisition owing to its ability of overcoming reconstruction limitations due to k-space truncations. The performance of this approach is evaluated using both simulated and real MR brain images, and compared with existing techniques. The results demonstrate that the proposed SFA based on phase correction achieves higher image quality than the initial SFA or the projection-onto-convex sets (POCS) method.     

Magnetic resonance image reconstruction using trained geometric directions in 2D redundant wavelets domain and non-convex optimization

Reducing scanning time is significantly important for MRI. Compressed sensing has shown promising results by undersampling the k-space data to speed up imaging. Sparsity of an image plays an important role in compressed sensing MRI to reduce the image artifacts. Recently, the method of patch-based directional wavelets (PBDW) which trains geometric directions from undersampled data has been proposed. It has better performance in preserving image edges than conventional sparsifying transforms. However, obvious artifacts are presented in the smooth region when the data are highly undersampled. In addition, the original PBDW-based method does not hold obvious improvement for radial and fully 2D random sampling patterns. In this paper, the PBDW-based MRI reconstruction is improved from two aspects: 1) An efficient non-convex minimization algorithm is modified to enhance image quality; 2) PBDW are extended into shift-invariant discrete wavelet domain to enhance the ability of transform on sparsifying piecewise smooth image features. Numerical simulation results on vivo magnetic resonance images demonstrate that the proposed method outperforms the original PBDW in terms of removing artifacts and preserving edges.